Robótica
241
33
Solving Rubik’s Cube with a robot hand
We’ve trained a pair of neural networks to solve the Rubik’s Cube with a human-like robot hand. The neural networks are trained entirely in simulation, using the same reinforcement learning code as OpenAI Five paired with a new technique called Automatic Domain Randomization (ADR). The system can handle situations it never saw during training, such as being prodded by a…
Learning concepts with energy functions
We’ve developed an energy-based model that can quickly learn to identify and generate instances of concepts, such as near, above, between, closest, and furthest, expressed as sets of 2d points. Our model learns these concepts after only five demonstrations. We also show cross-domain transfer: we use concepts learned in a 2d particle environment to solve tasks on a 3-dimensional physics-based…
Learning dexterity
We’ve trained a human-like robot hand to manipulate physical objects with unprecedented dexterity.
Ingredients for robotics research
We’re releasing eight simulated robotics environments and a Baselines implementation of Hindsight Experience Replay, all developed for our research over the past year. We’ve used these environments to train models which work on physical robots. We’re also releasing a set of requests for robotics research.
Generalizing from simulation
Our latest robotics techniques allow robot controllers, trained entirely in simulation and deployed on physical robots, to react to unplanned changes in the environment as they solve simple tasks. That is, we’ve used these techniques to build closed-loop systems rather than open-loop ones as before.
Meta-learning for wrestling
We show that for the task of simulated robot wrestling, a meta-learning agent can learn to quickly defeat a stronger non-meta-learning agent, and also show that the meta-learning agent can adapt to physical malfunction.
Faster physics in Python
We’re open-sourcing a high-performance Python library for robotic simulation using the MuJoCo engine, developed over our past year of robotics research.
Robots that learn
We’ve created a robotics system, trained entirely in simulation and deployed on a physical robot, which can learn a new task after seeing it done once.
Roboschool
We are releasing Roboschool: open-source software for robot simulation, integrated with OpenAI Gym.
Spam detection in the physical world
We’ve created the world’s first Spam-detecting AI trained entirely in simulation and deployed on a physical robot.
Team update
The OpenAI team is now 45 people. Together, we’re pushing the frontier of AI capabilities—whether by validating novel ideas, creating new software systems, or deploying machine learning on robots.